TY - GEN
T1 - When to Use What
T2 - 61st Annual Meeting of the Association for Computational Linguistics, ACL 2023
AU - Pei, Kevin
AU - Jindal, Ishan
AU - Chang, Kevin Chen Chuan
AU - Zhai, Chengxiang
AU - Li, Yunyao
N1 - Publisher Copyright:
© 2023 Association for Computational Linguistics.
PY - 2023
Y1 - 2023
N2 - Open Information Extraction (OpenIE) has been used in the pipelines of various NLP tasks. Unfortunately, there is no clear consensus on which models to use for which tasks. Muddying things further is the lack of comparisons that take differing training sets into account. In this paper, we present an application-focused empirical survey of neural OpenIE models, training sets, and benchmarks in an effort to help users choose the most suitable OpenIE systems for their applications. We find that the different assumptions made by different models and datasets have a statistically significant effect on performance, making it important to choose the most appropriate model for one's applications. We demonstrate the applicability of our recommendations on a downstream Complex QA application.
AB - Open Information Extraction (OpenIE) has been used in the pipelines of various NLP tasks. Unfortunately, there is no clear consensus on which models to use for which tasks. Muddying things further is the lack of comparisons that take differing training sets into account. In this paper, we present an application-focused empirical survey of neural OpenIE models, training sets, and benchmarks in an effort to help users choose the most suitable OpenIE systems for their applications. We find that the different assumptions made by different models and datasets have a statistically significant effect on performance, making it important to choose the most appropriate model for one's applications. We demonstrate the applicability of our recommendations on a downstream Complex QA application.
UR - http://www.scopus.com/inward/record.url?scp=85174391557&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85174391557&partnerID=8YFLogxK
U2 - 10.18653/v1/2023.acl-long.53
DO - 10.18653/v1/2023.acl-long.53
M3 - Conference contribution
AN - SCOPUS:85174391557
T3 - Proceedings of the Annual Meeting of the Association for Computational Linguistics
SP - 929
EP - 949
BT - Long Papers
PB - Association for Computational Linguistics (ACL)
Y2 - 9 July 2023 through 14 July 2023
ER -